© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88203
    Prev
    Next
    INDEX
    Explanations

    Ambani, Albani

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ك
    0.84
    ير
    0.74
    ل
    0.73
    الي
    0.72
    رس
    0.72
    ح
    0.72
    است
    0.71
    ה
    0.71
    Су
    0.71
    ру
    0.69
    POSITIVE LOGITS
    thiophene
    0.61
    
    0.56
     וש
    0.55
     aon
    0.55
    ją
    0.54
     ребят
    0.54
    bindingFields
    0.54
     thiab
    0.53
     طریقے
    0.53
    ५
    0.52
    Activations Density 0.000%

    No Known Activations